OpenCode

Which models can your machine actually run? Magnitude is a 100% free, open source desktop app that: - profiles your hardware and runs sample calculations - predicts tok/s for every model before you download - recommends the best models, from fast to smart Pick your models and it handles the rest: - downloads and tunes the models for your hardware - connects agents like pi, opencode, hermes in one click - runs models on demand as your agent works Works on whatever hardware you already own: MacBook (Intel or Apple Silicon), Mac Mini, Mac Studio, DGX Spark, Strix Halo, any NVIDIA/AMD GPU, or just a CPU Download it on macOS, Windows, or Linux: Open source:

• magnitude.dev
• github.com

A significant benefit is the ability to compare different agents and models when performing the same task. While performance is important, cost is also a crucial factor. Identifying a model that achieves the desired outcome at a considerably lower price point provides the kind of adaptability required by users of artificial intelligence.

@quxiaoyin

We just launched Agentsky @agentsky_dev, world’s 1st Agent Market! OpenRouter is for models. AgentSky is for agents. > Use 40+ agents—Claude Code, Codex, OpenCode, Hermes, Pi in your browser(even your phone!) or via one API. All without installing or setting up anything. > Hit Codex Astra’s weekly limit? Hand off to another agent such as OpenCode + DeepSeek V4.1 in browser without losing any context. > You can compare any agent + model directly in browser and that's how I found Astra costs $5.3 while deepseek v4.1 cost $0.12 on the same dashboard task. (I actually preferred deepseek) > Try it at

• agentsky.d

in the next version of OpenCode we added /btw which is a long awaited feature it lets you ask a quick question without interrupting the current session - i use it to get status updates on long running work

She’s right. This cheapens a thing that is actually really cool (stealth drops) The fact that they made a twitter account for the stealth model is super “fellow kids” core

@maria_rcks

very disappointed all of the model providers (opencode, openrouter, whatever) > released 'union alpha' without telling us it was a crappy model router > kudos to the cloudflare guys for telling people what they're getting > AND FUCK union alpha

Union Alpha is now in Codex!! The speed is insane over 300 to 400 tokens a second, 262k context, images in, and it's free for a week. It's a good timing too, most of the Codex usage is basically gone right now. Zai did this exact thing in August: Ox Alpha showed up unnamed, free for a week, built for agentic coding, and a week later it was GLM-5.3-Flash. So what model do you guys think it is?

@opencode

Union Alpha (stealth model) is free for the next week > - no data training - built for agentic coding - supports images > let's see what you can do

union alpha vs kimi k3 tested both models with same prompt at highest reasoning available > union alpha took 30 minutes to make this > k3 took 10 minutes to make this stealth model looks on par with Kimi, it could actually be the kimi next mode can't do more tests now as it's almost unusable right now so gonna try again in morning for now here's output, which one did better?

@notjazii

is union alpha working for anyone? > been trying to make it work for the fast few hours and it just keep giving me error > tried it in opencode and via openrouter too but still same > worst stealth model launch ever > all i wanna do is test few of my prompts, is that too much to ask?

What happens when your AI model becomes good enough to build its own infrastructure? Zhipu just found out. Their AI model GLM-5.3 helped build and optimize the inference system that serves GLM-5.3-Flash to users. The model improving the system that runs the model. 100,000+ Chinese-made AI accelerators. Nobody had deployed at this scale on that hardware before. Limited memory. Incomplete ecosystem. Most of it undocumented. The Infra Agent powered by GLM-5.3 did the engineering work. Found bugs in kernels. Fixed concurrency bottlenecks. Studied optimization patterns from other codebases and applied them to its own inference. First successful run to production ready in two weeks. Throughput tripled. Then it went live anonymously as "Ox-Alpha" on OpenCode and OpenRouter. Became the most-used model on both platforms in six days. 62 trillion tokens processed. Zhipu's own words: "The model optimizes the system. The system runs the model." They added: "We have not yet reached full recursive self-improvement. B

Stealth models in 2026: Hunter Alpha → Xiaomi MiMo-V2 Owl Alpha → Meituan LongCat Pony Alpha → GLM-5 Ox Alpha → GLM-5.3-Flash Now Union Alpha is free for a week on OpenCode and OpenRouter.

• z.ai

Today we're launching @opencode on Clawi. Code in your browser in a secure cloud environment—without ever giving an agent access to your personal computer. To celebrate, we’re increasing all agent limits at no extra cost: Basic + Pro: 2 agents, Ultra: 6 parallel agents.

in the latest opencode2 you can optionally mention a different model to use for subagents very useful, i use it to get reviews from smarter models

Coding Agent 也能变成可复现的 Research Agent。 OpenResearch 补上的不是更长的 prompt，而是一套追踪假设、实验和证据的工作台。今天 GitHub Trending 页面截取时显示新增 531 stars。 它让 Claude Code、Codex、OpenCode、Cursor 在隔离的 git worktree 中并行探索；每次实验关联代码快照、日志、diff、结果与产物，形成可复现的 experiment tree。还能自动循环：提出想法→改代码→跑实验→读证据→决定下一步。 任务可在本机、SSH 或集群运行，记录默认保存在本地。注意 Windows 仍是 beta；远程服务没有应用级鉴权，同机多人环境要额外小心。

• github.com

Multi-agent systems usually hide the coordination layer inside an orchestrator. @Plasma__AI Plasma AI launched Radio, and puts that coordination in a room you can actually watch. Radio is a shared chat room where agents from different providers can talk directly. Without a shared channel, each agent sees only its own conversation, leaving humans to relay outputs between separate tools. Radio replaces that handoff with a link, and Plasma says any agent that can fetch a URL can join, including Claude Code, Codex, Cursor, OpenCode, and Grok.

@Plasma__AI

Introducing Radio: A chat room for your agents. > Create a channel, share the link, and bring your teammates and agents together. No sign up required. > Try it today at

• radio.plasma.ai

OpenResearch，一个开源的本地科研工作台，把 Claude Code、Codex、OpenCode、Cursor 这 4 款变成研究 Agent，每个研究方向单开一个 Agent 会话和一个独立的 git 工作树，互不干扰。 实验按 git 树来管，每次运行都存一份当时提交的快照，日志、改动、结果文件全挂在产生它们的那次运行下面，回头查得清楚。 GitHub： 它能把整个循环自动跑起来，提出想法、改代码、起实验、看结果、决定下一步试什么，多个 Agent 并行探索，实验树保留谱系。 每个方向一个工作树这个设计我觉得是最实在的一点，隔离干净了后面的事都好办。 同一份代码快照本地能跑，远程 GPU 机器上也能跑，Slurm、Kubernetes、Ray、Modal 都接，浏览器留在笔记本上看进度就行。 项目、对话、运行记录全存自己机器上，建项目和跑实验都不会把代码传出去。 有桌面版和命令行版两种，还能按关键词找论文、直接拉 arXiv 文章进来读。

• github.com

Plannotator 让 Agent 写的计划，我们可以在网页上打开审查，在段落上划线、写批注，点一下就把意见整包送回给 Agent 改。 代码写完也一样，改动以左右对照的形式打开，逐行评论、直接给建议代码，GitHub 和 GitLab 上的 PR 也能拉进来评。 GitHub： Claude Code、Codex、Copilot CLI、Gemini CLI、OpenCode 等 9 个编码 Agent 都接了，一个安装脚本自动识别装了哪些，对应配置一并配好。 Agent 生成的 HTML 页面也能直接渲染出来在上面批注，评论时还能随手问 AI，或者让它先跑一轮审查把评论贴到改动上。 计划、改动、批注全存本地，不收使用数据。想让审计划这一步从终端里挪出来、能划线能批注的，可以装上试试。

• github.com